Real-time forecasting of near-field tsunami waveforms at coastal areas using a regularized extreme learning machine

Mulia, Iyan E.; Asano, Toshiyuki; Nagayama, Aiko

doi:10.1016/j.coastaleng.2015.11.010

Cited by 29 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because Indonesia does not have all of them, so in this research, we propose three new input data to substitute them; coastal topography in west coast Banten, Sunda Strait bathymetry, and rainfall intensity from six stations in Banten. There are several methods used to estimate tsunami inundation zone; extreme learning machine (ELM) [9], weighted overlay [10] [11], and analytical hierarchy process (AHP) [12]. The method is used in this study is the weighted overlay.…”

Section: Methodsmentioning

confidence: 99%

Determination of Inundation Zone Using Artificial Intelligence as a Basis for Infrastructure Development in Special Economic Areas of Tanjung Lesung Banten

Oktavianti¹,

Septyandy²,

Indra³

2020

Proceedings of Tourism Development Centre International Conference

View full text Add to dashboard Cite

According to history, Sunda Strait has experienced several tsunamis recorded in the tsunami catalog caused by several geological phenomena such as Krakatau eruption (416, 1883, and 1928), earthquake (1722, 1852, and 1958), and other suspected causes of land failure in the form of landslides both on the coast and on a submarine (1851, 1883, and 1889). One of the most recent tsunami incidents in the Sunda Strait was the tsunami on December 22, 2018, which triggered a flank collapse as the volcano part built on the caldera's steep wall resulting from 1883 eruption. According to The Indonesia National Disaster Management Agency (BNPB), the number of victims of the Sunda Strait tsunami died at 437 people, and losses for tourism ranged from Rp150 billion. One example of a successful tourism area that could rise after the tsunami is Pucket Beach, Thailand. This beach, affected by the 2004 Indian Ocean Tsunami, can increase the number of tourist arrivals even exceeded the number of visits before the tsunami caused by mapping vulnerability areas and comprehensive risk analysis. This study's aim implies these methods because the majority of tourism areas in Indonesia have not applied the master plan that includes the tsunami risk area, one of which is in the special economic zone (KEK) of Tanjung Lesung. To anticipate future tsunamis, an inundation zone model of tsunami waves will arrive at the coast. Inundation zones or tsunami wave runoff zones are generated from non-linear relationships between the Sunda Strait bathymetry, tide gauge signals, west coast of Banten topography, and rainfall on Sunda Strait tsunami 2018 using artificial intelligence by weighted overlay method. The inundation resulting from this research can be used as a reference for the local government for infrastructure development that supports Tanjung Lesung tourism.

show abstract

Section: Methodsmentioning

confidence: 99%

Determination of Inundation Zone Using Artificial Intelligence as a Basis for Infrastructure Development in Special Economic Areas of Tanjung Lesung Banten

Oktavianti¹,

Septyandy²,

Indra³

2020

Proceedings of Tourism Development Centre International Conference

View full text Add to dashboard Cite

show abstract

“…A tsunami waveform inversion has been widely used for studying the source mechanism (e.g., Gusman et al, ; Mulia, Gusman, Hossen, et al, ; Satake, ) and forecasting (e.g., Mulia et al, ; Tsushima et al, , ; Wei et al, ). In this study, for the tsunami waveform inversion analysis, we develop the Green's functions based on synthetic waveforms recorded at potential tsunameter locations originating from a unit amount of slip on the predefined subfaults.…”

Section: Methodsmentioning

confidence: 99%

An Optimized Array Configuration of Tsunami Observation Network Off Southern Java, Indonesia

et al. 2019

Self Cite

View full text Add to dashboard Cite

Historical records have proven that the southern coasts of Java, Indonesia, are prone to tsunamis. The existing tsunami observing system using bottom pressure gauges, also known as tsunameters, composes a global network but is too sparse for regional tsunami forecasts. The nearest tsunameter to Indonesia is located approximately 500‐km offshore, which is not very useful for the area, particularly for a tsunami source in eastern part of the Sunda megathrust. Here we propose a methodology to optimally place offshore tsunameters with the main consideration of operational costs, which is proportional to the number of observation points. We use a stochastic slip model of earthquakes with Mw 8.8–9.2 to generate multiple tsunami source realizations representing possible future events in the region. Based on the sources, we then identify a potential zone where an early tsunami detection is feasible. Furthermore, empirical orthogonal functions derived from tsunami simulations are used to determine the initial locations for tsunameter placement inside the specified zone. Finally, we apply an optimization scheme to improve the initial locations that facilitates both tsunami forecasts and source characterizations through a tsunami waveform inversion analysis. Our result indicates that six tsunameters are sufficient to efficiently cover the major seismogenic region in the study area.

show abstract

“…Other than that, here we assume the predefined source area, which is not applicable to a real case. A more comprehensive Green's function and an algorithm that can rapidly estimate the source area in real time (e.g., Mulia et al, ; Tsushima et al, ) are required in real applications. In this study, the maximum coastal tsunami heights at the same locations with the true state (Figure a) are stored and used to validate the results using equations .…”

Section: Methodsmentioning

confidence: 99%

“…Therefore, we are constrained by a short time period to produce reliable forecasts. The existing tsunami forecast algorithms based on tsunami WI, typically require 20–30 min of data to yield an accurate result (Gusman et al, ; Mulia et al, ; Tsushima et al, ). Relying only on tsunami WI that utilizes data from the existing observing systems may not be enough to deliver an accurate forecast within a few minutes in the Nankai Trough cases.…”

Section: Introductionmentioning

confidence: 99%

Preparing for the Future Nankai Trough Tsunami: A Data Assimilation and Inversion Analysis From Various Observational Systems

et al. 2017

Self Cite

View full text Add to dashboard Cite

The future Nankai Trough tsunami is one of the imminent threats to the Japanese coastal communities that could potentially cause a catastrophic event. As a part of the countermeasure efforts for such an occurrence, this study analyzes the efficacy of combining tsunami data assimilation (DA) and waveform inversion (WI). The DA is used to continuously refine a wavefield model whereas the WI is used to estimate the tsunami source. We consider a future scenario of the Nankai Trough tsunami recorded at various observational systems, including ocean bottom pressure (OBP) gauges, global positioning system (GPS) buoys, and ship height positioning data. Since most of the OBP gauges are located inside the source region, the recorded tsunami signals exhibit significant offsets from surface measurements due to coseismic seafloor deformation effects. Such biased data are not applicable to the standard DA, but can be taken into account in the WI. On the other hand, the use of WI for the ship data may not be practical because a considerably large precomputed tsunami database is needed to cope with the spontaneous ship locations. The DA is more suitable for such an observational system as it can be executed sequentially in time and does not require precomputed scenarios. Therefore, the combined approach of DA and WI allows us to concurrently make use of all observational resources. Additionally, we introduce a bias correction scheme for the OBP data to improve the accuracy, and an adaptive thinning of observations to determine the efficient number of observations.

show abstract

Real-time forecasting of near-field tsunami waveforms at coastal areas using a regularized extreme learning machine

Cited by 29 publications

References 35 publications

Determination of Inundation Zone Using Artificial Intelligence as a Basis for Infrastructure Development in Special Economic Areas of Tanjung Lesung Banten

Determination of Inundation Zone Using Artificial Intelligence as a Basis for Infrastructure Development in Special Economic Areas of Tanjung Lesung Banten

An Optimized Array Configuration of Tsunami Observation Network Off Southern Java, Indonesia

Preparing for the Future Nankai Trough Tsunami: A Data Assimilation and Inversion Analysis From Various Observational Systems

Contact Info

Product

Resources

About